MIT creates method to force AI to comply with safety rules
MIT researchers published HardFlow, a method enforcing hard safety constraints on flow-matching generative models' final outputs without retraining.
1
1 stories, newest first · one card per story
MIT researchers published HardFlow, a method enforcing hard safety constraints on flow-matching generative models' final outputs without retraining.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views